90d8ef6 verified 6 months ago

25.6 kB

	---
	language:
	- en
	library_name: sentence-transformers
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- dataset_size:314315
	- loss:AdaptiveLayerLoss
	- loss:MultipleNegativesRankingLoss
	base_model: microsoft/deberta-v3-small
	datasets:
	- stanfordnlp/snli
	- sentence-transformers/stsb
	metrics:
	- pearson_cosine
	- spearman_cosine
	- pearson_manhattan
	- spearman_manhattan
	- pearson_euclidean
	- spearman_euclidean
	- pearson_dot
	- spearman_dot
	- pearson_max
	- spearman_max
	- cosine_accuracy
	- cosine_accuracy_threshold
	- cosine_f1
	- cosine_f1_threshold
	- cosine_precision
	- cosine_recall
	- cosine_ap
	- dot_accuracy
	- dot_accuracy_threshold
	- dot_f1
	- dot_f1_threshold
	- dot_precision
	- dot_recall
	- dot_ap
	- manhattan_accuracy
	- manhattan_accuracy_threshold
	- manhattan_f1
	- manhattan_f1_threshold
	- manhattan_precision
	- manhattan_recall
	- manhattan_ap
	- euclidean_accuracy
	- euclidean_accuracy_threshold
	- euclidean_f1
	- euclidean_f1_threshold
	- euclidean_precision
	- euclidean_recall
	- euclidean_ap
	- max_accuracy
	- max_accuracy_threshold
	- max_f1
	- max_f1_threshold
	- max_precision
	- max_recall
	- max_ap
	widget:
	- source_sentence: The pitcher is pitching the ball in a game of baseball.
	sentences:
	- the lady digs into the ground
	- A group of people are sitting at tables.
	- The pitcher throws the ball.
	- source_sentence: People are conversing at a dining table under a canopy.
	sentences:
	- A canine is using his legs.
	- The people are creative.
	- People at a party are seated for dinner on the lawn.
	- source_sentence: Two teenage girls conversing next to lockers.
	sentences:
	- Girls talking about their problems next to lockers.
	- A group of people play in the ocean.
	- The man is testing the bike.
	- source_sentence: A young boy in a hoodie climbs a red slide sitting on a red and
	green checkered background.
	sentences:
	- People are buying food from a street vendor.
	- A boy is playing.
	- A dog outside digging.
	- source_sentence: A professional swimmer spits water out after surfacing while grabbing
	the hand of someone helping him back to land.
	sentences:
	- A group of people wait in a line.
	- A tourist has his picture taken on Easter Island.
	- The swimmer almost drowned after being sucked under a fast current.
	pipeline_tag: sentence-similarity
	model-index:
	- name: SentenceTransformer based on microsoft/deberta-v3-small
	results:
	- task:
	type: semantic-similarity
	name: Semantic Similarity
	dataset:
	name: Unknown
	type: unknown
	metrics:
	- type: pearson_cosine
	value: 0.7641416788909702
	name: Pearson Cosine
	- type: spearman_cosine
	value: 0.763668633314844
	name: Spearman Cosine
	- type: pearson_manhattan
	value: 0.7808845626705342
	name: Pearson Manhattan
	- type: spearman_manhattan
	value: 0.783960481366303
	name: Spearman Manhattan
	- type: pearson_euclidean
	value: 0.7714319160162553
	name: Pearson Euclidean
	- type: spearman_euclidean
	value: 0.7750607015673249
	name: Spearman Euclidean
	- type: pearson_dot
	value: 0.587659176024498
	name: Pearson Dot
	- type: spearman_dot
	value: 0.6010467058509925
	name: Spearman Dot
	- type: pearson_max
	value: 0.7808845626705342
	name: Pearson Max
	- type: spearman_max
	value: 0.783960481366303
	name: Spearman Max
	- task:
	type: binary-classification
	name: Binary Classification
	dataset:
	name: Unknown
	type: unknown
	metrics:
	- type: cosine_accuracy
	value: 0.6773826673743271
	name: Cosine Accuracy
	- type: cosine_accuracy_threshold
	value: 0.5830236673355103
	name: Cosine Accuracy Threshold
	- type: cosine_f1
	value: 0.7209834880077135
	name: Cosine F1
	- type: cosine_f1_threshold
	value: 0.5085207223892212
	name: Cosine F1 Threshold
	- type: cosine_precision
	value: 0.6137273007079102
	name: Cosine Precision
	- type: cosine_recall
	value: 0.873667299547247
	name: Cosine Recall
	- type: cosine_ap
	value: 0.7219177301725319
	name: Cosine Ap
	- type: dot_accuracy
	value: 0.6389415421942528
	name: Dot Accuracy
	- type: dot_accuracy_threshold
	value: 45.1016845703125
	name: Dot Accuracy Threshold
	- type: dot_f1
	value: 0.7090406632451638
	name: Dot F1
	- type: dot_f1_threshold
	value: 32.459449768066406
	name: Dot F1 Threshold
	- type: dot_precision
	value: 0.5775450202131569
	name: Dot Precision
	- type: dot_recall
	value: 0.9180663064115671
	name: Dot Recall
	- type: dot_ap
	value: 0.6795197111227502
	name: Dot Ap
	- type: manhattan_accuracy
	value: 0.6625217984684206
	name: Manhattan Accuracy
	- type: manhattan_accuracy_threshold
	value: 158.29489135742188
	name: Manhattan Accuracy Threshold
	- type: manhattan_f1
	value: 0.7041269465332466
	name: Manhattan F1
	- type: manhattan_f1_threshold
	value: 178.5047607421875
	name: Manhattan F1 Threshold
	- type: manhattan_precision
	value: 0.5921131248755228
	name: Manhattan Precision
	- type: manhattan_recall
	value: 0.8684095224185775
	name: Manhattan Recall
	- type: manhattan_ap
	value: 0.7054112942825768
	name: Manhattan Ap
	- type: euclidean_accuracy
	value: 0.6578967321252559
	name: Euclidean Accuracy
	- type: euclidean_accuracy_threshold
	value: 7.951424598693848
	name: Euclidean Accuracy Threshold
	- type: euclidean_f1
	value: 0.7015471831817645
	name: Euclidean F1
	- type: euclidean_f1_threshold
	value: 9.045232772827148
	name: Euclidean F1 Threshold
	- type: euclidean_precision
	value: 0.5888767720828789
	name: Euclidean Precision
	- type: euclidean_recall
	value: 0.8675332262304659
	name: Euclidean Recall
	- type: euclidean_ap
	value: 0.7024193897121154
	name: Euclidean Ap
	- type: max_accuracy
	value: 0.6773826673743271
	name: Max Accuracy
	- type: max_accuracy_threshold
	value: 158.29489135742188
	name: Max Accuracy Threshold
	- type: max_f1
	value: 0.7209834880077135
	name: Max F1
	- type: max_f1_threshold
	value: 178.5047607421875
	name: Max F1 Threshold
	- type: max_precision
	value: 0.6137273007079102
	name: Max Precision
	- type: max_recall
	value: 0.9180663064115671
	name: Max Recall
	- type: max_ap
	value: 0.7219177301725319
	name: Max Ap
	---

	# SentenceTransformer based on microsoft/deberta-v3-small

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) <!-- at revision a36c739020e01763fe789b4b85e2df55d6180012 -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	- Training Dataset:
	- [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli)
	- Language: en
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)

	### Full Model Architecture

	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model
	(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
	)
	```

	## Usage

	### Direct Usage (Sentence Transformers)

	First install the Sentence Transformers library:

	```bash
	pip install -U sentence-transformers
	```

	Then you can load this model and run inference.
	```python
	from sentence_transformers import SentenceTransformer

	# Download from the 🤗 Hub
	model = SentenceTransformer("bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerAll")
	# Run inference
	sentences = [
	'A professional swimmer spits water out after surfacing while grabbing the hand of someone helping him back to land.',
	'The swimmer almost drowned after being sucked under a fast current.',
	'A group of people wait in a line.',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities.shape)
	# [3, 3]
	```

	<!--
	### Direct Usage (Transformers)

	<details><summary>Click to see the direct usage in Transformers</summary>

	</details>
	-->

	<!--
	### Downstream Usage (Sentence Transformers)

	You can finetune this model on your own dataset.

	<details><summary>Click to expand</summary>

	</details>
	-->

	<!--
	### Out-of-Scope Use

	List how the model may foreseeably be misused and address what users ought not to do with the model.
	-->

	## Evaluation

	### Metrics

	#### Semantic Similarity

	* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| pearson_cosine \| 0.7641 \|
	\| spearman_cosine \| 0.7637 \|
	\| pearson_manhattan \| 0.7809 \|
	\| spearman_manhattan \| 0.784 \|
	\| pearson_euclidean \| 0.7714 \|
	\| spearman_euclidean \| 0.7751 \|
	\| pearson_dot \| 0.5877 \|
	\| spearman_dot \| 0.601 \|
	\| pearson_max \| 0.7809 \|
	\| spearman_max \| 0.784 \|

	#### Binary Classification

	* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)

	\| Metric \| Value \|
	\|:-----------------------------\|:-----------\|
	\| cosine_accuracy \| 0.6774 \|
	\| cosine_accuracy_threshold \| 0.583 \|
	\| cosine_f1 \| 0.721 \|
	\| cosine_f1_threshold \| 0.5085 \|
	\| cosine_precision \| 0.6137 \|
	\| cosine_recall \| 0.8737 \|
	\| cosine_ap \| 0.7219 \|
	\| dot_accuracy \| 0.6389 \|
	\| dot_accuracy_threshold \| 45.1017 \|
	\| dot_f1 \| 0.709 \|
	\| dot_f1_threshold \| 32.4594 \|
	\| dot_precision \| 0.5775 \|
	\| dot_recall \| 0.9181 \|
	\| dot_ap \| 0.6795 \|
	\| manhattan_accuracy \| 0.6625 \|
	\| manhattan_accuracy_threshold \| 158.2949 \|
	\| manhattan_f1 \| 0.7041 \|
	\| manhattan_f1_threshold \| 178.5048 \|
	\| manhattan_precision \| 0.5921 \|
	\| manhattan_recall \| 0.8684 \|
	\| manhattan_ap \| 0.7054 \|
	\| euclidean_accuracy \| 0.6579 \|
	\| euclidean_accuracy_threshold \| 7.9514 \|
	\| euclidean_f1 \| 0.7015 \|
	\| euclidean_f1_threshold \| 9.0452 \|
	\| euclidean_precision \| 0.5889 \|
	\| euclidean_recall \| 0.8675 \|
	\| euclidean_ap \| 0.7024 \|
	\| max_accuracy \| 0.6774 \|
	\| max_accuracy_threshold \| 158.2949 \|
	\| max_f1 \| 0.721 \|
	\| max_f1_threshold \| 178.5048 \|
	\| max_precision \| 0.6137 \|
	\| max_recall \| 0.9181 \|
	\| max_ap \| 0.7219 \|

	<!--
	## Bias, Risks and Limitations

	What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.
	-->

	<!--
	### Recommendations

	What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.
	-->

	## Training Details

	### Training Dataset

	#### stanfordnlp/snli

	* Dataset: [stanfordnlp/snli](https://huggingface.co/datasets/stanfordnlp/snli) at [cdb5c3d](https://huggingface.co/datasets/stanfordnlp/snli/tree/cdb5c3d5eed6ead6e5a341c8e56e669bb666725b)
	* Size: 314,315 training samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| label \|
	\|:--------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------------------------\|:-----------------------------\|
	\| type \| string \| string \| int \|
	\| details \| <ul><li>min: 5 tokens</li><li>mean: 16.62 tokens</li><li>max: 62 tokens</li></ul> \| <ul><li>min: 4 tokens</li><li>mean: 9.46 tokens</li><li>max: 29 tokens</li></ul> \| <ul><li>0: 100.00%</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| label \|
	\|:---------------------------------------------------------------------------\|:-------------------------------------------------\|:---------------\|
	\| <code>A person on a horse jumps over a broken down airplane.</code> \| <code>A person is outdoors, on a horse.</code> \| <code>0</code> \|
	\| <code>Children smiling and waving at camera</code> \| <code>There are children present</code> \| <code>0</code> \|
	\| <code>A boy is jumping on skateboard in the middle of a red bridge.</code> \| <code>The boy does a skateboarding trick.</code> \| <code>0</code> \|
	* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
	```json
	{
	"loss": "MultipleNegativesRankingLoss",
	"n_layers_per_step": -1,
	"last_layer_weight": 1,
	"prior_layers_weight": 1,
	"kl_div_weight": 1.2,
	"kl_temperature": 1.2
	}
	```

	### Evaluation Dataset

	#### sentence-transformers/stsb

	* Dataset: [sentence-transformers/stsb](https://huggingface.co/datasets/sentence-transformers/stsb) at [ab7a5ac](https://huggingface.co/datasets/sentence-transformers/stsb/tree/ab7a5ac0e35aa22088bdcf23e7fd99b220e53308)
	* Size: 1,500 evaluation samples
	* Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| sentence1 \| sentence2 \| score \|
	\|:--------\|:----------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|:---------------------------------------------------------------\|
	\| type \| string \| string \| float \|
	\| details \| <ul><li>min: 5 tokens</li><li>mean: 14.77 tokens</li><li>max: 45 tokens</li></ul> \| <ul><li>min: 6 tokens</li><li>mean: 14.74 tokens</li><li>max: 49 tokens</li></ul> \| <ul><li>min: 0.0</li><li>mean: 0.47</li><li>max: 1.0</li></ul> \|
	* Samples:
	\| sentence1 \| sentence2 \| score \|
	\|:--------------------------------------------------\|:------------------------------------------------------\|:------------------\|
	\| <code>A man with a hard hat is dancing.</code> \| <code>A man wearing a hard hat is dancing.</code> \| <code>1.0</code> \|
	\| <code>A young child is riding a horse.</code> \| <code>A child is riding a horse.</code> \| <code>0.95</code> \|
	\| <code>A man is feeding a mouse to a snake.</code> \| <code>The man is feeding a mouse to the snake.</code> \| <code>1.0</code> \|
	* Loss: [<code>AdaptiveLayerLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#adaptivelayerloss) with these parameters:
	```json
	{
	"loss": "MultipleNegativesRankingLoss",
	"n_layers_per_step": -1,
	"last_layer_weight": 1,
	"prior_layers_weight": 1,
	"kl_div_weight": 1.2,
	"kl_temperature": 1.2
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 16
	- `learning_rate`: 5e-06
	- `weight_decay`: 1e-07
	- `warmup_ratio`: 0.33
	- `save_safetensors`: False
	- `fp16`: True
	- `push_to_hub`: True
	- `hub_model_id`: bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerAlln
	- `hub_strategy`: checkpoint
	- `batch_sampler`: no_duplicates

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: steps
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 16
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `learning_rate`: 5e-06
	- `weight_decay`: 1e-07
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 3
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.33
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: False
	- `save_on_each_node`: False
	- `save_only_model`: False
	- `restore_callback_states_from_checkpoint`: False
	- `no_cuda`: False
	- `use_cpu`: False
	- `use_mps_device`: False
	- `seed`: 42
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: False
	- `fp16`: True
	- `fp16_opt_level`: O1
	- `half_precision_backend`: auto
	- `bf16_full_eval`: False
	- `fp16_full_eval`: False
	- `tf32`: None
	- `local_rank`: 0
	- `ddp_backend`: None
	- `tpu_num_cores`: None
	- `tpu_metrics_debug`: False
	- `debug`: []
	- `dataloader_drop_last`: False
	- `dataloader_num_workers`: 0
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: False
	- `ignore_data_skip`: False
	- `fsdp`: []
	- `fsdp_min_num_params`: 0
	- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
	- `fsdp_transformer_layer_cls_to_wrap`: None
	- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch
	- `optim_args`: None
	- `adafactor`: False
	- `group_by_length`: False
	- `length_column_name`: length
	- `ddp_find_unused_parameters`: None
	- `ddp_bucket_cap_mb`: None
	- `ddp_broadcast_buffers`: False
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `skip_memory_metrics`: True
	- `use_legacy_prediction_loop`: False
	- `push_to_hub`: True
	- `resume_from_checkpoint`: None
	- `hub_model_id`: bobox/DeBERTaV3-small-SentenceTransformer-AdaptiveLayerAlln
	- `hub_strategy`: checkpoint
	- `hub_private_repo`: False
	- `hub_always_push`: False
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `eval_do_concat_batches`: True
	- `fp16_backend`: auto
	- `push_to_hub_model_id`: None
	- `push_to_hub_organization`: None
	- `mp_parameters`:
	- `auto_find_batch_size`: False
	- `full_determinism`: False
	- `torchdynamo`: None
	- `ray_scope`: last
	- `ddp_timeout`: 1800
	- `torch_compile`: False
	- `torch_compile_backend`: None
	- `torch_compile_mode`: None
	- `dispatch_batches`: None
	- `split_batches`: None
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `batch_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| max_ap \| spearman_cosine \|
	\|:------:\|:-----:\|:-------------:\|:------:\|:------:\|:---------------:\|
	\| None \| 0 \| - \| 5.4171 \| - \| 0.4276 \|
	\| 0.1501 \| 1474 \| 4.9879 \| - \| - \| - \|
	\| 0.3000 \| 2947 \| - \| 2.6463 \| 0.6840 \| - \|
	\| 0.3001 \| 2948 \| 3.2669 \| - \| - \| - \|
	\| 0.4502 \| 4422 \| 2.6363 \| - \| - \| - \|
	\| 0.6000 \| 5894 \| - \| 1.8436 \| 0.7014 \| - \|
	\| 0.6002 \| 5896 \| 2.192 \| - \| - \| - \|
	\| 0.7503 \| 7370 \| 0.8208 \| - \| - \| - \|
	\| 0.9000 \| 8841 \| - \| 1.5551 \| 0.7065 \| - \|
	\| 0.9003 \| 8844 \| 0.6161 \| - \| - \| - \|
	\| 1.0504 \| 10318 \| 1.0301 \| - \| - \| - \|
	\| 1.2000 \| 11788 \| - \| 1.1883 \| 0.7131 \| - \|
	\| 1.2004 \| 11792 \| 1.8209 \| - \| - \| - \|
	\| 1.3505 \| 13266 \| 1.6887 \| - \| - \| - \|
	\| 1.5001 \| 14735 \| - \| 1.1067 \| 0.7119 \| - \|
	\| 1.5006 \| 14740 \| 1.6114 \| - \| - \| - \|
	\| 1.6506 \| 16214 \| 1.0691 \| - \| - \| - \|
	\| 1.8001 \| 17682 \| - \| 1.0872 \| 0.7183 \| - \|
	\| 1.8007 \| 17688 \| 0.3982 \| - \| - \| - \|
	\| 1.9507 \| 19162 \| 0.3659 \| - \| - \| - \|
	\| 2.1001 \| 20629 \| - \| 0.9642 \| 0.7221 \| - \|
	\| 2.1008 \| 20636 \| 1.1702 \| - \| - \| - \|
	\| 2.2508 \| 22110 \| 1.4984 \| - \| - \| - \|
	\| 2.4001 \| 23576 \| - \| 0.9437 \| 0.7200 \| - \|
	\| 2.4009 \| 23584 \| 1.4609 \| - \| - \| - \|
	\| 2.5510 \| 25058 \| 1.4477 \| - \| - \| - \|
	\| 2.7001 \| 26523 \| - \| 0.9428 \| 0.7216 \| - \|
	\| 2.7010 \| 26532 \| 0.5802 \| - \| - \| - \|
	\| 2.8511 \| 28006 \| 0.3297 \| - \| - \| - \|
	\| 3.0 \| 29469 \| - \| 0.9532 \| 0.7219 \| - \|
	\| None \| 0 \| - \| 2.4079 \| 0.7219 \| 0.7637 \|


	### Framework Versions
	- Python: 3.10.13
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.1.2
	- Accelerate: 0.30.1
	- Datasets: 2.19.2
	- Tokenizers: 0.19.1

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@inproceedings{reimers-2019-sentence-bert,
	title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
	author = "Reimers, Nils and Gurevych, Iryna",
	booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
	month = "11",
	year = "2019",
	publisher = "Association for Computational Linguistics",
	url = "https://arxiv.org/abs/1908.10084",
	}
	```

	#### AdaptiveLayerLoss
	```bibtex
	@misc{li20242d,
	title={2D Matryoshka Sentence Embeddings},
	author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
	year={2024},
	eprint={2402.14776},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```

	#### MultipleNegativesRankingLoss
	```bibtex
	@misc{henderson2017efficient,
	title={Efficient Natural Language Response Suggestion for Smart Reply},
	author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
	year={2017},
	eprint={1705.00652},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->